#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Provably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…

Benchmark of 265 real vulnerability-introducing code changes across nine C, C++, and Rust projects, with paired review tasks, Docker sandbox, judge,…

Code for the paper Certified Unlearning for Neural Networks, ICML 2025

Google Tensor Cracks

Automated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…

Code, response logs and labels for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

Cryptographically signed delegation receipts for AI agents. Define exactly what an AI can and can't do — signed, verifiable, tamper-proof.

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

finance domain specific red-teaming benchmark evaluation rubric

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Automated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX…

Scan LLM outputs and AI-generated content for data exfiltration signals (EchoLeak, CVE-2025-32711) before they reach users or downstream systems

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

A small go harness that uses Ollama to orchestrate LLMs in a restricted process flow

Implementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"

Voice-based detective interrogation game. Mistral Large 3 + Voxtral STT + ElevenLabs TTS. Built for the Mistral Worldwide Hackathon 2026.